Matches in SemOpenAlex for { <https://semopenalex.org/work/W4304014530> ?p ?o ?g. }
- W4304014530 abstract "In recent years, supervised or unsupervised learning-based MVS methods achieved excellent performance compared with traditional methods. However, these methods only use the probability volume computed by cost volume regularization to predict reference depths and this manner cannot mine enough information from the probability volume. Furthermore, the unsupervised methods usually try to use two-step or additional inputs for training which make the procedure more complicated. In this paper, we propose the DS-MVSNet, an end-to-end unsupervised MVS structure with the source depths synthesis. To mine the information in probability volume, we creatively synthesize the source depths by splattering the probability volume and depth hypotheses to source views. Meanwhile, we propose the adaptive Gaussian sampling and improved adaptive bins sampling approach that improve the depths hypotheses accuracy. On the other hand, we utilize the source depths to render the reference images and propose depth consistency loss and depth smoothness loss. These can provide additional guidance according to photometric and geometric consistency in different views without additional inputs. Finally, we conduct a series of experiments on the DTU dataset and Tanks $&$ Temples dataset that demonstrate the efficiency and robustness of our DS-MVSNet compared with the state-of-the-art methods." @default.
- W4304014530 created "2022-10-10" @default.
- W4304014530 creator A5018863416 @default.
- W4304014530 creator A5022950764 @default.
- W4304014530 creator A5038802973 @default.
- W4304014530 creator A5039667088 @default.
- W4304014530 creator A5076518693 @default.
- W4304014530 date "2022-10-10" @default.
- W4304014530 modified "2023-10-16" @default.
- W4304014530 title "DS-MVSNet: Unsupervised Multi-view Stereo via Depth Synthesis" @default.
- W4304014530 cites W1539230104 @default.
- W4304014530 cites W1901129140 @default.
- W4304014530 cites W2009422376 @default.
- W4304014530 cites W2021716052 @default.
- W4304014530 cites W2108417695 @default.
- W4304014530 cites W2112174119 @default.
- W4304014530 cites W2205172244 @default.
- W4304014530 cites W2338968644 @default.
- W4304014530 cites W2471962767 @default.
- W4304014530 cites W2519683295 @default.
- W4304014530 cites W2565639579 @default.
- W4304014530 cites W2738551266 @default.
- W4304014530 cites W2926429807 @default.
- W4304014530 cites W2962793285 @default.
- W4304014530 cites W2963906250 @default.
- W4304014530 cites W2967693513 @default.
- W4304014530 cites W2982336381 @default.
- W4304014530 cites W2997111976 @default.
- W4304014530 cites W3034530552 @default.
- W4304014530 cites W3034564916 @default.
- W4304014530 cites W3034600477 @default.
- W4304014530 cites W3035477536 @default.
- W4304014530 cites W3097305369 @default.
- W4304014530 cites W3108346482 @default.
- W4304014530 cites W3152935628 @default.
- W4304014530 cites W3159272845 @default.
- W4304014530 cites W3159981575 @default.
- W4304014530 cites W3170262190 @default.
- W4304014530 cites W3170748769 @default.
- W4304014530 cites W3195763721 @default.
- W4304014530 cites W3202682771 @default.
- W4304014530 cites W3204267695 @default.
- W4304014530 cites W3204354488 @default.
- W4304014530 doi "https://doi.org/10.1145/3503161.3548352" @default.
- W4304014530 hasPublicationYear "2022" @default.
- W4304014530 type Work @default.
- W4304014530 citedByCount "1" @default.
- W4304014530 countsByYear W43040145302022 @default.
- W4304014530 crossrefType "proceedings-article" @default.
- W4304014530 hasAuthorship W4304014530A5018863416 @default.
- W4304014530 hasAuthorship W4304014530A5022950764 @default.
- W4304014530 hasAuthorship W4304014530A5038802973 @default.
- W4304014530 hasAuthorship W4304014530A5039667088 @default.
- W4304014530 hasAuthorship W4304014530A5076518693 @default.
- W4304014530 hasBestOaLocation W43040145301 @default.
- W4304014530 hasConcept C102634674 @default.
- W4304014530 hasConcept C104317684 @default.
- W4304014530 hasConcept C105795698 @default.
- W4304014530 hasConcept C106131492 @default.
- W4304014530 hasConcept C119857082 @default.
- W4304014530 hasConcept C121332964 @default.
- W4304014530 hasConcept C134306372 @default.
- W4304014530 hasConcept C140779682 @default.
- W4304014530 hasConcept C154945302 @default.
- W4304014530 hasConcept C163716315 @default.
- W4304014530 hasConcept C185592680 @default.
- W4304014530 hasConcept C19499675 @default.
- W4304014530 hasConcept C20556612 @default.
- W4304014530 hasConcept C2776135515 @default.
- W4304014530 hasConcept C2776436953 @default.
- W4304014530 hasConcept C2781395549 @default.
- W4304014530 hasConcept C2988416141 @default.
- W4304014530 hasConcept C31972630 @default.
- W4304014530 hasConcept C33923547 @default.
- W4304014530 hasConcept C41008148 @default.
- W4304014530 hasConcept C55493867 @default.
- W4304014530 hasConcept C62520636 @default.
- W4304014530 hasConcept C63479239 @default.
- W4304014530 hasConcept C8038995 @default.
- W4304014530 hasConceptScore W4304014530C102634674 @default.
- W4304014530 hasConceptScore W4304014530C104317684 @default.
- W4304014530 hasConceptScore W4304014530C105795698 @default.
- W4304014530 hasConceptScore W4304014530C106131492 @default.
- W4304014530 hasConceptScore W4304014530C119857082 @default.
- W4304014530 hasConceptScore W4304014530C121332964 @default.
- W4304014530 hasConceptScore W4304014530C134306372 @default.
- W4304014530 hasConceptScore W4304014530C140779682 @default.
- W4304014530 hasConceptScore W4304014530C154945302 @default.
- W4304014530 hasConceptScore W4304014530C163716315 @default.
- W4304014530 hasConceptScore W4304014530C185592680 @default.
- W4304014530 hasConceptScore W4304014530C19499675 @default.
- W4304014530 hasConceptScore W4304014530C20556612 @default.
- W4304014530 hasConceptScore W4304014530C2776135515 @default.
- W4304014530 hasConceptScore W4304014530C2776436953 @default.
- W4304014530 hasConceptScore W4304014530C2781395549 @default.
- W4304014530 hasConceptScore W4304014530C2988416141 @default.
- W4304014530 hasConceptScore W4304014530C31972630 @default.
- W4304014530 hasConceptScore W4304014530C33923547 @default.
- W4304014530 hasConceptScore W4304014530C41008148 @default.
- W4304014530 hasConceptScore W4304014530C55493867 @default.